NMRPeak: a ready-to-use intelligent system for molecular structure elucidation enabled by synergistic cross-modal learning

TL;DR

NMRPeak is an integrated machine learning system that advances molecular structure elucidation from NMR spectra by combining prediction, retrieval, and generation tasks with experimental data, achieving high accuracy and bridging the simulation-experiment gap.

Contribution

It introduces a unified, experimentally grounded cross-modal learning framework with novel tokenization and similarity metrics, enabling accurate, automated molecular structure elucidation.

Findings

Achieves over 95% top-1 accuracy in molecular retrieval.

Attains approximately 75% top-1 accuracy in stereochemistry-aware structure generation.

Constructs the largest NMR spectrum benchmark with 1.8 million spectra.

Abstract

One-dimensional nuclear magnetic resonance (NMR) spectroscopy is essential for molecular structure elucidation in organic synthesis, drug discovery, natural product characterization, and metabolomics, yet its interpretation remains heavily dependent on expert knowledge and difficult to scale. Although machine learning has been applied to NMR spectrum prediction, library retrieval, and structure generation, these tasks have evolved in isolation using simulated data and incompatible spectral representations, limiting their utility under real experimental scenarios. Here we present NMRPeak, a unified cross-modal learning system that integrates these three tasks through experimentally grounded design. We curate approximately 1.8 million experimental and simulated spectra to construct the largest benchmark for NMR-based structure elucidation and systematically quantify the distribution shift between these domains. We introduce a chemically-aware adaptive tokenizer that dynamically balances discretization granularity to preserve spectral semantics while controlling vocabulary size, and an assignment-free peak-aware similarity metric that enables direct comparison between predicted and experimental spectra. Through a unified molecule-to-spectrum paradigm and synergistic coupling of prediction, retrieval, and generation modules, NMRPeak achieves transformative performance on experimental benchmarks: it overcomes the longstanding simulation-to-experiment gap in spectrum prediction while delivering over 95% top-1 accuracy in molecular retrieval and approximately 75% top-1 accuracy in stereochemistry-aware de novo structure generation. These capabilities establish a foundation for automated, high-throughput molecular structure elucidation in organic synthesis, drug discovery, and chemical biology.